Research Dl Paper-notes Tts RADMMM: Multilingual Multiaccented Multispeaker TTS with RADTTS RADMMM: Multilingual Multiaccented Multispeaker TTS with RADTTS Rohan Badlani, Rafael Valle, Kevin J. Shih, João Felipe Santos, Siddharth Gururani, Bryan Catanzaro (NVIDIA)
Research Dl Paper-notes Tts Mixer-TTS Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings by Oktai Tatanov, Stanislav Beliaev, Boris Ginsburg (NVIDIA, Santa Clara).